Architectures for the Intelligent AI-Ready Enterprise : Building Real-World Solutions with MongoDB.

Format:

Book

Author/Creator:

Bialek, Boris.

Contributor:

Arbulu, Sebastian Rojas.

Hedgecock, Taylor.

Scharf, Jim.

Language:

English

Subjects (All):

MongoDB.

Physical Description:

1 online resource (510 pages)

Edition:

1st ed.

Place of Publication:

[S.l.]: Packt Publishing, 2025.

Birmingham : Packt Publishing, Limited, 2025.

Summary:

Create AI-ready enterprise solutions with MongoDB and discover how to design intelligent architectures that transform data into innovation, efficiency, and real business value Key Features Complete guide covering GenAI to agentic AI, semantic protection to multi-agent systems 25+ proven AI use cases delivering measurable impact across 6+.

Contents:

Intro

FM

Foreword

Note from the author

Acknowledgements

Contributors

Preface

Part 1: AI and Key Concepts

Chapter 1: AI Modernization to Innovation

Understanding innovation: Creating new value

Strategic inflection points: Andy Grove's theory applied to AI

Navigating the AI inflection point

Understanding modernization: The often-overlooked prerequisite

Common modernization strategies

Where innovation meets modernization: The AI intersection

The AI implementation pitfall: When innovation lacks foundation

Modern data platforms: The backbone of AI-ready transformation

Why modern data platforms are necessary

Enabling innovation through agility and speed

Simplifying modernization without starting over

Powering AI at scale

Summary

References

Chapter 2: What Sets GenAI, RAG, and Agentic AI Apart

How AI evolved: From theory to ChatGPT

A small walk into history

AlphaGo and the turning point in AI

The emergence of LLMs

GenAI: Creating new content from patterns

How GenAI works

Limitations and challenges of GenAI

From data to vectors

The embedding models and "embedders"

Vector databases and their importance

Chunking strategies for AI applications

Semantic search: Putting vectors to work

Beyond keyword matching

Multimodal applications of semantic search

RAG: Enhancing LLMs with contextual data

How RAG works

Beyond RAG: Hybrid search approaches

Reranking: Refining search results

Agentic AI: Automating decision-making and reasoning

Agentic AI foundation

What is an agent?

Digital experts or multi-agent systems: Collaborative problem-solving

How agentic AI works

Chapter 3: The System of Action

Building an AI-ready data foundation

What is a system of action?

Unified data access architecture.

Ensuring data quality and consistency

Real-time context and RAG

Scalability, availability, and performance

Governance, security, and compliance

Model training and fine-tuning

Practical considerations for AI data design

A good data structure is critical

Data flow

Operationalizing a system of action database

Deployment patterns

Performance monitoring and optimization

Cost management and resource allocation

Maintenance workflows and data lifecycle management

Migration strategies from legacy systems

Team training and adoption considerations

Chapter 4: Trustworthy AI, Compliance, and Data Governance

Why ethical AI matters

The rising stakes of AI implementation

Defining the core concepts

Ethical frameworks: From principles to practice

Bridging principles and implementation

Bias audits

Ethical review boards

Transparent documentation

Stakeholder engagement

Navigating the regulatory landscape

Healthcare

Financial services

Building trustworthy and responsible AI

Safeguarding data

Protection and privacy requirements

Building robust AI data governance

Managing risk: assessment and mitigation strategies

Risk assessment

Practical risk management approaches

Transparency in action: Explainability mechanisms

AI transparency

AI explainability

The business case for explainable AI

Operationalizing trustworthy AI through governance

The road ahead: Emerging trends and future directions

Evolution of AI governance

Persistent challenges and opportunities

Chapter 5: Modernization Using AI

The modernization challenge

Motivations for modernization

Business imperatives: Competitive pressure and innovation

Technical limitations: The growing burden of legacy architecture.

Why AI alone isn't the answer

Unlocking innovation with AI-powered modernization

Start with the right data foundation

Automating the modernization factory process

Orchestration: how the factory is automated

Where AI accelerates the process

Analysis

Test generation

Code transformation and testing

Deploying and migrating

Establishing a repeatable modernization process

Part 2: Real-World Case Studies and Implementations

Chapter 6: Practical Applications of Agentic and GenAI in Manufacturing - Part 1

The path to success in manufacturing AI

GenAI-powered supply chain optimization

Multi-level planning approaches

Inventory classification and optimization approaches

ABC analysis and its limitations

MCIC and the need for GenAI

AI and MongoDB for inventory optimization

GenAI-powered inventory classification

Methodology for implementing GenAI-powered inventory classification

Atlas: Unified AI infrastructure

GenAI inventory classification demo: A visual walkthrough

Step 1: Starting with basic classification

Step 2: Generating new AI-powered criteria

Step 3: Integrating new criteria into classification

Step 4: Weighting and running analysis

Raw material management via agentic AI

Demand forecasting and inventory optimization

Benefits of MongoDB for inventory management

Reimagining inventory management for Industry 5.0

Chapter 7: Practical Applications of Agentic and GenAI in Manufacturing - Part 2

Predictive maintenance and multi-agent collaboration

Optimal maintenance strategy

Current state and challenges

How AI and MongoDB help

Stage 1: Machine prioritization

Stage 2: Failure prediction

Stage 3: Repair plan generators

Stage 4: Maintenance guidance generation

Multi-agent collaboration system.

Optimizing a production environment

Knowledge management and preservation

The challenge of institutional knowledge and AI-powered solutions

Real-time knowledge application

Hyper-personalized in-cabin experiences

Challenges and AI-powered solutions for in-car voice assistants

GenAI: transforming in-car assistants

Solution architecture: MongoDB Atlas and Google Cloud integration

Advanced agentic architecture: MongoDB Atlas and Google Cloud integration

RAG implementation challenges for vehicle manuals

Google Cloud and MongoDB: Better together

Strategic advantages of AI-integrated in-cabin systems

Fleet management and optimization

Scheduler agent for fleet operations

Logical and physical architecture

MongoDB for fleet scheduler

Agent profile and instructions

Short-term and long-term memory

Connected fleet incident advisor

Incident advisor architecture

Data types and storage

Advantages of MongoDB for fleet management

The expanding role of AI in manufacturing

Chapter 8: AI-Driven Strategies for Media and Telecommunication Industries

Evolving landscape of media and telecommunication

Content discovery and personalization

Content suggestions and personalization platform

Content suggestions and personalization

Content summarization and reformatting

Keyword and entity extraction

Automatic creation of insights and summaries

Search generative experiences (SGEs)

Smart conversational interfaces

Gamified learning experiences

Service assurance

Agentic AIOps for network management

Building AI-powered network systems for telecommunications

The next era of AI-powered operations

Fraud detection and prevention

The expanding role of AI in media and telecommunication

Differential pricing

Video search and clipping

Summary.

References

Chapter 9: Cognigy's Voice and Chatbots in the Time of Agentic AI

The evolution from rule-based to goal-oriented AI

Case study: How a Tier-1 airline responded to crisis

The limitations that held us back

The agentic AI breakthrough

Why data is the lifeblood of agentic AI

The scope of modern data requirements

MongoDB's role in enabling real-time intelligence

Real-world application: transforming retail customer experience

The technical foundation for seamless integration

Real-time performance in critical moments

When systems are pushed to their limits

The complexity behind simple requests

Scaling excellence, not mistakes

The mathematics of transformation

Demonstrated results across industries

The foundation for sustainable growth

Personalization isn't magic, it's data mastery

The architecture of intelligent personalization

The technical foundation for personalization excellence

The stakes of accuracy

The comprehensive requirements for AI excellence

Governance and compliance framework

Chapter 10: Harnessing AI to Transform the Retail Industry

Semantic search powered by vector search

Transforming retail search

Building a unified customer view

Evolving from reactive to proactive

Personalized marketing and content generation

Meeting the content demands of modern retail with GenAI

Accelerating personalized content with GenAI and LLMs

Leveraging modern databases for scalable, AI-driven marketing

How agentic AI is revolutionizing adaptive marketing in retail

Demand forecasting and predictive analytics

AI-driven demand forecasting for smarter inventory and supply chain management

How GenAI is reshaping predictive analytics in retail

Transforming predictive analytics with agentic AI in retail.

Digitizing in-store interactions with intelligence.

Notes:

Electronic book.

Description based on publisher supplied metadata and other sources.

ISBN:

1-80611-714-2

1-80611-715-0

OCLC:

1535359838